| license: apache-2.0 | |
| tags: | |
| - generated_from_trainer | |
| metrics: | |
| - precision | |
| - recall | |
| - f1 | |
| - accuracy | |
| model-index: | |
| - name: bert-finetuned-cross-ner | |
| results: [] | |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You | |
| should probably proofread and complete it, then remove this comment. --> | |
| # bert-finetuned-cross-ner | |
| This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset. | |
| It achieves the following results on the evaluation set: | |
| - Loss: 0.1761 | |
| - Precision: 0.8267 | |
| - Recall: 0.8619 | |
| - F1: 0.8439 | |
| - Accuracy: 0.9561 | |
| ## Model description | |
| More information needed | |
| ## Intended uses & limitations | |
| More information needed | |
| ## Training and evaluation data | |
| More information needed | |
| ## Training procedure | |
| ### Training hyperparameters | |
| The following hyperparameters were used during training: | |
| - learning_rate: 2e-05 | |
| - train_batch_size: 8 | |
| - eval_batch_size: 8 | |
| - seed: 42 | |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 | |
| - lr_scheduler_type: linear | |
| - num_epochs: 3 | |
| - mixed_precision_training: Native AMP | |
| ### Training results | |
| | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | | |
| |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| | |
| | 0.2037 | 1.0 | 2607 | 0.1973 | 0.7633 | 0.8122 | 0.7870 | 0.9449 | | |
| | 0.1264 | 2.0 | 5214 | 0.1709 | 0.8102 | 0.8484 | 0.8289 | 0.9542 | | |
| | 0.0817 | 3.0 | 7821 | 0.1761 | 0.8267 | 0.8619 | 0.8439 | 0.9561 | | |
| ### Framework versions | |
| - Transformers 4.28.0 | |
| - Pytorch 2.0.1+cu118 | |
| - Datasets 2.12.0 | |
| - Tokenizers 0.13.3 | |